+
    ˜°³j,  ã                   ód   € ^ RI Hu Ht ^ RIHt ^RIHt RR.t ! R R]4      t	 ! R R]4      t
R# )é    N©ÚTensor)ÚModuleÚPairwiseDistanceÚCosineSimilarityc                   ól   a a€ ] tR t^
t oRt. ROtR	V3R lV 3R llltV3R lR ltV3R ltRt	Vt
V ;t# )
r   aè  
Computes the pairwise distance between input vectors, or between columns of input matrices.

Distances are computed using ``p``-norm, with constant ``eps`` added to avoid division by zero
if ``p`` is negative, i.e.:

.. math ::
    \mathrm{dist}\left(x, y\right) = \left\Vert x-y + \epsilon e \right\Vert_p,

where :math:`e` is the vector of ones and the ``p``-norm is given by.

.. math ::
    \Vert x \Vert _p = \left( \sum_{i=1}^n  \vert x_i \vert ^ p \right) ^ {1/p}.

Args:
    p (real, optional): the norm degree. Can be negative. Default: 2
    eps (float, optional): Small value to avoid division by zero.
        Default: 1e-6
    keepdim (bool, optional): Determines whether or not to keep the vector dimension.
        Default: False
Shape:
    - Input1: :math:`(N, D)` or :math:`(D)` where `N = batch dimension` and `D = vector dimension`
    - Input2: :math:`(N, D)` or :math:`(D)`, same shape as the Input1
    - Output: :math:`(N)` or :math:`()` based on input dimension.
      If :attr:`keepdim` is ``True``, then :math:`(N, 1)` or :math:`(1)` based on input dimension.

Examples:
    >>> pdist = nn.PairwiseDistance(p=2)
    >>> input1 = torch.randn(100, 128)
    >>> input2 = torch.randn(100, 128)
    >>> output = pdist(input1, input2)
c                ó0   <€ V ^8„  d   QhRS[ RS[ RS[RR/# )é   ÚpÚepsÚkeepdimÚreturnN©ÚfloatÚbool)ÚformatÚ__classdict__s   "€ÚZ/home/luca/screen-checking/.venv/lib/python3.14/site-packages/torch/nn/modules/distance.pyÚ__annotate__ÚPairwiseDistance.__annotate__1   s-   ø€ ÷ ñ ÙðÙ#(ðÙ:>ðà	ñó    c                óH   <€ \         SV `  4        Wn        W n        W0n        R # ©N)ÚsuperÚ__init__Únormr   r   )Úselfr   r   r   Ú	__class__s   &&&&€r   r   ÚPairwiseDistance.__init__1   s   ø€ ô 	‰ÑÔØŒ	ØŒØŽr   c                ó,   <€ V ^8„  d   QhRS[ RS[ RS[ /# ©r
   Úx1Úx2r   r   )r   r   s   "€r   r   r   9   s'   ø€ ÷ Nñ N™&ð N¡fð N±ñ Nr   c                óp   € \         P                  ! WV P                  V P                  V P                  4      # ©z
Runs the forward pass.
)ÚFÚpairwise_distancer   r   r   ©r   r"   r#   s   &&&r   ÚforwardÚPairwiseDistance.forward9   s'   € ô ×"Ò" 2¨4¯9©9°d·h±hÀÇÁÓMÐMr   c                ó>   <€ V ^8„  d   Qh/ S[ ;R&   S[ ;R&   S[;R&   # )r
   r   r   r   r   )r   r   s   "€r   r   r   
   s/   ø‡ ‚ ñF �KñG ñH 
�JñI ñJ �MòK r   )r   r   r   )r   r   r   )g       @g�íµ ÷Æ°>F©Ú__name__Ú
__module__Ú__qualname__Ú__firstlineno__Ú__doc__Ú__constants__r   r)   Ú__annotate_func__Ú__static_attributes__Ú__classdictcell__Ú__classcell__©r   r   s   @@r   r   r   
   s0   ù‡ € ñòB /€M÷
õ ÷Nð N÷_ … r   c                   ól   a a€ ] tR t^@t oRtRR.tR
V3R lV 3R llltV3R lR ltV3R ltR	t	Vt
V ;t# )r   aK  Returns cosine similarity between :math:`x_1` and :math:`x_2`, computed along `dim`.

.. math ::
    \text{similarity} = \dfrac{x_1 \cdot x_2}{\max(\Vert x_1 \Vert _2 \cdot \Vert x_2 \Vert _2, \epsilon)}.

Args:
    dim (int, optional): Dimension where cosine similarity is computed. Default: 1
    eps (float, optional): Small value to avoid division by zero.
        Default: 1e-8
Shape:
    - Input1: :math:`(\ast_1, D, \ast_2)` where D is at position `dim`
    - Input2: :math:`(\ast_1, D, \ast_2)`, same number of dimensions as x1, matching x1 size at dimension `dim`,
      and broadcastable with x1 at other dimensions.
    - Output: :math:`(\ast_1, \ast_2)`

Examples:
    >>> input1 = torch.randn(100, 128)
    >>> input2 = torch.randn(100, 128)
    >>> cos = nn.CosineSimilarity(dim=1, eps=1e-6)
    >>> output = cos(input1, input2)
Údimr   c                ó*   <€ V ^8„  d   QhRS[ RS[RR/# )r
   r9   r   r   N©Úintr   )r   r   s   "€r   r   ÚCosineSimilarity.__annotate__[   s"   ø€ ÷ ñ ™Cð ©%ð ¸4ñ r   c                ó<   <€ \         SV `  4        Wn        W n        R # r   )r   r   r9   r   )r   r9   r   r   s   &&&€r   r   ÚCosineSimilarity.__init__[   s   ø€ Ü‰ÑÔØŒØŽr   c                ó,   <€ V ^8„  d   QhRS[ RS[ RS[ /# r!   r   )r   r   s   "€r   r   r=   `   s"   ø€ ÷ ?ñ ?™&ð ?¡fð ?±ñ ?r   c                óZ   € \         P                  ! WV P                  V P                  4      # r%   )r&   Úcosine_similarityr9   r   r(   s   &&&r   r)   ÚCosineSimilarity.forward`   s!   € ô ×"Ò" 2¨4¯8©8°T·X±XÓ>Ð>r   c                ó2   <€ V ^8„  d   Qh/ S[ ;R&   S[;R&   # )r
   r9   r   r;   )r   r   s   "€r   r   r=   @   s   ø‡ ‚ ñ0 
�Hñ1 ñ2 
�Jò3 r   )r9   r   )é   g:Œ0âŽyE>r,   r7   s   @@r   r   r   @   s1   ù‡ € ñð, ˜E�N€M÷õ ÷
?ð ?÷A … r   )Útorch.nn.functionalÚnnÚ
functionalr&   Útorchr   Úmoduler   Ú__all__r   r   © r   r   Ú<module>rM      s9   ðß Ð Ý å ð Ð1Ð
2€ô3N�vô 3Nôl$?�vö $?r   